Improved spoken term detection using support vector machines based on lattice context consistency

We propose an improved spoken term detection approach that uses support vector machines trained with lattice context consistency. The basic idea is that the same term usually have similar context, while quite different context usually implies the terms are different. Support vector machine can be trained using query context feature vectors obtained from the lattice to estimate better scores for ranking, and significant improvements can be obtained. This process can be performed iteratively and integrated with the pseudo relevance feedback in acoustic feature space proposed previously, both offering further improvements.